{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q6KWIF6LD3SRKEZXSCAPGQM5IS","short_pith_number":"pith:Q6KWIF6L","schema_version":"1.0","canonical_sha256":"87956417cb1ee51513379080f3419d4498cca300197565307647dee1837baccf","source":{"kind":"arxiv","id":"2601.15284","version":2},"attestation_state":"computed","paper":{"title":"Walk through Paintings: Egocentric World Models from Internet Priors","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Bagchi, Homanga Bharadhwaj, Martial Hebert, Pavel Tokmakov, Yu-Xiong Wang, Zhipeng Bao","submitted_at":"2026-01-21T18:59:32Z","abstract_excerpt":"What if a video generation model could not only imagine a plausible future, but the correct one -- accurately reflecting how the world changes with each action? We answer this by presenting the Egocentric World Model (EgoWM), a simple, architecture-agnostic method that transforms any pre-trained video diffusion model into an action-conditioned world model, enabling precisely controllable future prediction. Rather than training from scratch, we repurpose the rich world priors of Internet-scale video models by injecting appropriately compressed motor commands through lightweight conditioning lay"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.15284","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-21T18:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"837f1aabcc6bb37b360468b9c854ab9c93134d72330dd40984e30e7863702797","abstract_canon_sha256":"d4b0fe0d9119102f0b3d6fba323b749cf4f294d3cddce806eed2ccc787b35cac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87956417cb1ee51513379080f3419d4498cca300197565307647dee1837baccf","last_reissued_at":"2026-07-30T01:19:28.012092Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:19:28.012092Z"},"graph_snapshot":{"paper":{"title":"Walk through Paintings: Egocentric World Models from Internet Priors","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Bagchi, Homanga Bharadhwaj, Martial Hebert, Pavel Tokmakov, Yu-Xiong Wang, Zhipeng Bao","submitted_at":"2026-01-21T18:59:32Z","abstract_excerpt":"What if a video generation model could not only imagine a plausible future, but the correct one -- accurately reflecting how the world changes with each action? We answer this by presenting the Egocentric World Model (EgoWM), a simple, architecture-agnostic method that transforms any pre-trained video diffusion model into an action-conditioned world model, enabling precisely controllable future prediction. Rather than training from scratch, we repurpose the rich world priors of Internet-scale video models by injecting appropriately compressed motor commands through lightweight conditioning lay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.15284","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.15284/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.15284","created_at":"2026-07-30T01:19:28.017470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.15284v2","created_at":"2026-07-30T01:19:28.017470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15284","created_at":"2026-07-30T01:19:28.017470+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6KWIF6LD3SR","created_at":"2026-07-30T01:19:28.017470+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6KWIF6LD3SRKEZX","created_at":"2026-07-30T01:19:28.017470+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6KWIF6L","created_at":"2026-07-30T01:19:28.017470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.01164","citing_title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24761","citing_title":"Drift-Resistant Navigation World Model with Anchored Epipolar Guidance","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20388","citing_title":"How You Move Tells What You'll Do: Trajectory-Conditioned Egocentric Prediction","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2603.11755","citing_title":"Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS","json":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS.json","graph_json":"https://pith.science/api/pith-number/Q6KWIF6LD3SRKEZXSCAPGQM5IS/graph.json","events_json":"https://pith.science/api/pith-number/Q6KWIF6LD3SRKEZXSCAPGQM5IS/events.json","paper":"https://pith.science/paper/Q6KWIF6L"},"agent_actions":{"view_html":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS","download_json":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS.json","view_paper":"https://pith.science/paper/Q6KWIF6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.15284&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6KWIF6LD3SRKEZXSCAPGQM5IS/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6KWIF6LD3SRKEZXSCAPGQM5IS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS/action/storage_attestation","attest_author":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS/action/author_attestation","sign_citation":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS/action/citation_signature","submit_replication":"https://pith.science/pith/Q6KWIF6LD3SRKEZXSCAPGQM5IS/action/replication_record"}},"created_at":"2026-07-30T01:19:28.017470+00:00","updated_at":"2026-07-30T01:19:28.017470+00:00"}